sched: Fix cross-sched-class wakeup preemption

Instead of dealing with sched classes inside each check_preempt_curr()
implementation, pull out this logic into the generic wakeup preemption
path.

This fixes a hang in KVM (and others) where we are waiting for the
stop machine thread to run ...

Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Tested-by: Marcelo Tosatti <mtosatti@redhat.com>
Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1288891946.2039.31.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 26 insertions, 11 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 36a088018fe0..dc91a4d09ac3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -560,18 +560,8 @@ struct rq {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
-        rq->curr->sched_class->check_preempt_curr(rq, p, flags);
 
-        /*
-         * A queue event has occurred, and we're going to schedule.  In
-         * this case, we can save a useless back to back clock update.
-         */
-        if (test_tsk_need_resched(p))
-                rq->skip_clock_update = 1;
-}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
 static inline int cpu_of(struct rq *rq)
 {
@@ -2118,6 +2108,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                 p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+{
+        const struct sched_class *class;
+
+        if (p->sched_class == rq->curr->sched_class) {
+                rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+        } else {
+                for_each_class(class) {
+                        if (class == rq->curr->sched_class)
+                                break;
+                        if (class == p->sched_class) {
+                                resched_task(rq->curr);
+                                break;
+                        }
+                }
+        }
+
+        /*
+         * A queue event has occurred, and we're going to schedule.  In
+         * this case, we can save a useless back to back clock update.
+         */
+        if (test_tsk_need_resched(rq->curr))
+                rq->skip_clock_update = 1;
+}
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot: